利用随机过程理论研究了遗忘因子最小二乘法 (FFLS)的有界收敛性 ,给出了参数估计误差的上界 .分析表明 :i)对于时不变确定性系统 ,FFLS算法产生的参数估计以指数速度收敛于真参数 ;ii)对于时不变随机系统 ,FFLS算法给出有界均方估计误差 ;iii)对于时变随机系统 ,FFLS算法可以跟踪时变参数 ,且跟踪误差有界 . The stochastic process theory is used to study the bounded convergence of the forgetting factor least squares method (FFLS), and the upper bound of the parameter estimation error is given. The analysis shows that: i) For the time invariant deterministic system, the parameter estimation The exponential speed converges to the true parameter; ii) the FFLS algorithm gives the bounded mean square estimation error for time-invariant stochastic systems; iii) the FFLS algorithm can track time-varying parameters and the tracking error is bounded for time-varying stochastic systems.